Closed ashwinvaswani closed 4 years ago
Bhaiya I would like to take this issue
kindly guide how to proceed
Sure. Basically, we're fixing to standard practice of using only OpenCV to load images. However in some places we cannot avoid the usage of PIL because torchvision transforms use PIL format.
In Badminton.py, remove all instances of loading images with PIL ie the code Image.open() with cv2.imread and if this image is passed to detect_image, then while passing, set the PIL_image_flag parameter as False.
Currently, image formatting is slightly off with different parts of code using images loaded by cv2 and some using images loaded by PIL. Since the formats are different, there are some bugs. We will stick to OpenCV for image loading and all image operations from now on so changing PIL stuff wherever possible to OpenCV.